Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth
For the untargeted analysis of the metabolome of biological samples with liquid chromatography–mass spectrometry (LC-MS), high-dimensional data sets containing many different metabolites are obtained. Since the utilization of these complex data is challenging, different machine learning approaches h...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Metabolites |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1989/12/1/5 |
| _version_ | 1797492075932942336 |
|---|---|
| author | Soeren Wenck Marina Creydt Jule Hansen Florian Gärber Markus Fischer Stephan Seifert |
| author_facet | Soeren Wenck Marina Creydt Jule Hansen Florian Gärber Markus Fischer Stephan Seifert |
| author_sort | Soeren Wenck |
| collection | DOAJ |
| description | For the untargeted analysis of the metabolome of biological samples with liquid chromatography–mass spectrometry (LC-MS), high-dimensional data sets containing many different metabolites are obtained. Since the utilization of these complex data is challenging, different machine learning approaches have been developed. Those methods are usually applied as black box classification tools, and detailed information about class differences that result from the complex interplay of the metabolites are not obtained. Here, we demonstrate that this information is accessible by the application of random forest (RF) approaches and especially by surrogate minimal depth (SMD) that is applied to metabolomics data for the first time. We show this by the selection of important features and the evaluation of their mutual impact on the multi-level classification of white asparagus regarding provenance and biological identity. SMD enables the identification of multiple features from the same metabolites and reveals meaningful biological relations, proving its high potential for the comprehensive utilization of high-dimensional metabolomics data. |
| first_indexed | 2024-03-10T00:58:24Z |
| format | Article |
| id | doaj.art-2798ffbbdb634564b8bc3eb7e64bb894 |
| institution | Directory Open Access Journal |
| issn | 2218-1989 |
| language | English |
| last_indexed | 2024-03-10T00:58:24Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metabolites |
| spelling | doaj.art-2798ffbbdb634564b8bc3eb7e64bb8942023-11-23T14:39:25ZengMDPI AGMetabolites2218-19892021-12-01121510.3390/metabo12010005Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal DepthSoeren Wenck0Marina Creydt1Jule Hansen2Florian Gärber3Markus Fischer4Stephan Seifert5Institute of Food Chemistry, Hamburg School of Food Science, University of Hamburg, Grindelallee 117, 20146 Hamburg, GermanyInstitute of Food Chemistry, Hamburg School of Food Science, University of Hamburg, Grindelallee 117, 20146 Hamburg, GermanyInstitute of Food Chemistry, Hamburg School of Food Science, University of Hamburg, Grindelallee 117, 20146 Hamburg, GermanyInstitute of Food Chemistry, Hamburg School of Food Science, University of Hamburg, Grindelallee 117, 20146 Hamburg, GermanyInstitute of Food Chemistry, Hamburg School of Food Science, University of Hamburg, Grindelallee 117, 20146 Hamburg, GermanyInstitute of Food Chemistry, Hamburg School of Food Science, University of Hamburg, Grindelallee 117, 20146 Hamburg, GermanyFor the untargeted analysis of the metabolome of biological samples with liquid chromatography–mass spectrometry (LC-MS), high-dimensional data sets containing many different metabolites are obtained. Since the utilization of these complex data is challenging, different machine learning approaches have been developed. Those methods are usually applied as black box classification tools, and detailed information about class differences that result from the complex interplay of the metabolites are not obtained. Here, we demonstrate that this information is accessible by the application of random forest (RF) approaches and especially by surrogate minimal depth (SMD) that is applied to metabolomics data for the first time. We show this by the selection of important features and the evaluation of their mutual impact on the multi-level classification of white asparagus regarding provenance and biological identity. SMD enables the identification of multiple features from the same metabolites and reveals meaningful biological relations, proving its high potential for the comprehensive utilization of high-dimensional metabolomics data.https://www.mdpi.com/2218-1989/12/1/5classificationcharacterizationwhite asparagusLC-MSmetabolomicsrandom forest |
| spellingShingle | Soeren Wenck Marina Creydt Jule Hansen Florian Gärber Markus Fischer Stephan Seifert Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth Metabolites classification characterization white asparagus LC-MS metabolomics random forest |
| title | Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth |
| title_full | Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth |
| title_fullStr | Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth |
| title_full_unstemmed | Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth |
| title_short | Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth |
| title_sort | opening the random forest black box of the metabolome by the application of surrogate minimal depth |
| topic | classification characterization white asparagus LC-MS metabolomics random forest |
| url | https://www.mdpi.com/2218-1989/12/1/5 |
| work_keys_str_mv | AT soerenwenck openingtherandomforestblackboxofthemetabolomebytheapplicationofsurrogateminimaldepth AT marinacreydt openingtherandomforestblackboxofthemetabolomebytheapplicationofsurrogateminimaldepth AT julehansen openingtherandomforestblackboxofthemetabolomebytheapplicationofsurrogateminimaldepth AT floriangarber openingtherandomforestblackboxofthemetabolomebytheapplicationofsurrogateminimaldepth AT markusfischer openingtherandomforestblackboxofthemetabolomebytheapplicationofsurrogateminimaldepth AT stephanseifert openingtherandomforestblackboxofthemetabolomebytheapplicationofsurrogateminimaldepth |